Quickstart: Integrate uncensored AI

Set the base URL and authenticate

Change your client configuration to point at our API. We support the standard OpenAI SDKs, so you only need to update the base_url and provide your API key. Sign up via Google or email to get a key instantly without a phone number. The key is displayed immediately after creation.

Copycurl https://api.chatgptbezcenzury.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Authentication works exactly like the official API. If the key is invalid, you receive a 401 error. If you have no prepaid credit, the API returns a 402 error. Errors and refusals do not consume your balance.

Send your first request

Use the standard /v1/chat/completions endpoint to generate text. Send your prompt as a JSON object with the model ID set to uncensored. This model runs on our servers and does not refuse lawful adult, fictional, or controversial topics. It is not GPT or Claude, but it follows the same interface.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatgptbezcenzury.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Each request supports up to 100,000 tokens for the combined prompt and completion. The maximum output per request is 16,000 tokens. If you do not specify max_tokens, the default limit is 2,048 tokens.

Use the Node SDK

Initialize the client with your API key and our base URL. The Node SDK handles the HTTP requests automatically. This approach keeps your code clean and allows you to swap vendors later if needed. Just remember that we offer a single model, not a router.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatgptbezcenzury.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Rate limits apply to keep the service stable. You can send 300 requests per minute per key. Concurrent requests are limited to 8 at the same time. The request body cannot exceed 8 MB. These limits are strict and enforced by the server.

Handle streaming responses

Enable streaming by setting the stream parameter to true. The API returns data via Server-Sent Events (SSE). Each chunk contains partial text and usage statistics in the final chunk. This method reduces perceived latency for long responses.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Streaming works well for applications that need immediate feedback. You can parse each chunk and display it to the user in real time. The model generates text token by token without waiting for the full completion.

Enable JSON mode

Force the model to output valid JSON by setting response_format to {"type": "json_object"}. This feature ensures structured data output for your applications. It is useful for parsing structured data without extra processing.

Function calling is also supported. You can define tools and let the model decide which one to use. The API handles the tool execution logic according to your client implementation.

Understand limits and errors

We enforce strict limits to ensure fair usage. The context window is 100,000 tokens. The maximum output is 16,000 tokens. You get 300 requests per minute. Concurrent requests are capped at 8. Request bodies must be under 8 MB.

Errors are handled via standard HTTP status codes. A 401 indicates an invalid key. A 402 means you need to add credit. A 429 signals that you have exceeded the rate limit. Credit never expires, so you can top up anytime.